PaddlePaddle / PaddleDetection

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Apache License 2.0
12.82k stars 2.89k forks source link

Segmentaion Fault paddlepaddleDetectionDev #6956

Closed MyraBaba closed 1 year ago

MyraBaba commented 2 years ago

问题确认 Search before asking

Bug组件 Bug Component

Inference

Bug描述 Describe the Bug

python3 deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_ppvehicle.yml --video_file=/data/Videos/hiv00038.mp4 --device=gpu deploy/pipeline/pipeline.py:24: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3, and in 3.9 it will stop working from collections import Sequence, defaultdict ----------- Running Arguments ----------- DET: batch_size: 1 model_dir: https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_ppvehicle.zip MOT: batch_size: 1 enable: true model_dir: https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_ppvehicle.zip skip_frame_num: -1 tracker_config: deploy/pipeline/config/tracker_config.yml VEHICLE_ATTR: batch_size: 8 color_threshold: 0.5 enable: false model_dir: https://bj.bcebos.com/v1/paddledet/models/pipeline/vehicle_attribute_model.zip type_threshold: 0.5 VEHICLE_PLATE: det_limit_side_len: 736 det_limit_type: min det_model_dir: https://bj.bcebos.com/v1/paddledet/models/pipeline/ch_PP-OCRv3_det_infer.tar.gz enable: false rec_batch_num: 6 rec_image_shape:


Multi-Object Tracking enabled DET model dir: /home/alp2080/.cache/paddle/infer_weights/mot_ppyoloe_l_36e_ppvehicle MOT model dir: /home/alp2080/.cache/paddle/infer_weights/mot_ppyoloe_l_36e_ppvehicle ----------- Model Configuration ----------- Model Arch: YOLO Transform Order: --transform op: Resize --transform op: Permute

video fps: 25, frame_count: 12525 Thread: 0; frame id: 0


C++ Traceback (most recent call last):

No stack trace in paddle, may be caused by external reasons.


Error Message Summary:

FatalError: Segmentation fault is detected by the operating system. [TimeInfo: Aborted at 1663332777 (unix time) try "date -d @1663332777" if you are using GNU date ] [SignalInfo: SIGSEGV (@0x0) received by PID 1553976 (TID 0x7fe07e306740) from PID 0 ]

Segmentation fault (core dumped)

复现环境 Environment

Linux PaddleDetecton latest dev

docker conatiner working , but in linux installed paddledetection its gives seg fault for tracking

Bug描述确认 Bug description confirmation

是否愿意提交PR? Are you willing to submit a PR?

nemonameless commented 2 years ago

https://github.com/PaddlePaddle/PaddleDetection/search?q=Segmentation+fault+is+detected+by+the+operating+system.&type=issues

  1. try --device=gpu, make sure your cuda cudnn is ok, see https://github.com/PaddlePaddle/PaddleDetection/issues/4934
  2. There are too many video frames. It is better to save them locally, or there may not be enough memory.